Estimasi ESTIMASI POTENSI PETIR BERBASIS POLA ELECTRIC FIELD MILL MENGGUNAKAN XGBOOST DAN BAYESIAN UPDATE

Ammar Jauhari

doi:10.23960/jitet.v14i3.10030

Ammar Jauhari
Politeknik Negeri Sriwijaya

DOI: https://doi.org/10.23960/jitet.v14i3.10030

Keywords Electric Field Mill, XGboost, Bayesian Update, Estimasi Petir, Machine Learning

Abstract Views (Last 12 Months)

7 Abstract Views

3 Downloads

Abstract

Abstrak. Petir merupakan fenomena atmosfer yang berisiko terhadap keselamatan manusia, sistem tenaga listrik, perangkat telekomunikasi, dan aktivitas luar ruang. Penelitian ini bertujuan mengembangkan model estimasi potensi petir berbasis pola Electric Field Mill (EFM) menggunakan XGBoost dan Bayesian Update. Data EFM diproses melalui tahapan prapemrosesan, ekstraksi fitur deret waktu, pembentukan skor potensi, pemodelan XGBoost, dan pembaruan probabilitas Bayesian. Fitur yang digunakan meliputi nilai medan listrik, perubahan medan listrik, rata-rata bergerak, simpangan baku, nilai maksimum absolut, dan kemiringan perubahan sinyal. Hasil pengujian menunjukkan bahwa XGBoost memperoleh MAE sebesar 1,673, RMSE sebesar 2,108, dan R² sebesar 0,990. Setelah dilakukan Bayesian Update, diperoleh MAE sebesar 5,846, RMSE sebesar 7,313, dan R² sebesar 0,882. Hasil tersebut menunjukkan bahwa XGBoost memberikan performa estimasi terbaik secara numerik, sedangkan Bayesian Update berperan sebagai mekanisme pembaruan probabilitas posterior yang lebih konservatif dan stabil. Penelitian ini dapat menjadi dasar awal pengembangan sistem peringatan dini petir berbasis EFM.

Downloads

Download data is not yet available.

References

National Weather Service, “Understanding Lightning Science,” National Oceanic and Atmospheric Administration, 2026.

Badan Meteorologi, Klimatologi, dan Geofisika, “Sambaran Petir Real-time,” BMKG, 2026.

M. A. B. Sidik, Z. Nawawi, M. I. Jambak, and Y. Z. Arief, “Development of Wireless Electric Field Mill for Atmospheric Electric Field Observation,” TELKOMNIKA, vol. 12, no. 4, pp. 1113–1122, 2014.

H. Shahroom, Z. Buntat, M. A. B. Sidik, Z. Nawawi, and M. I. Jambak, “Atmospheric Electric Field Measurement Advances in Southern Peninsular Malaysia,” in 2015 IEEE Conference on Energy Conversion (CENCON), 2015, pp. 116–121, doi: 10.1109/CENCON.2015.7409524.

M. A. da S. Ferro, J. Yamasaki, D. R. M. Pimentel, K. P. Naccarato, and M. M. F. Saba, “Lightning Risk Warnings Based on Atmospheric Electric Field Measurements in Brazil,” Journal of Aerospace Technology and Management, vol. 3, no. 3, pp. 301–310, 2011, doi: 10.5028/jatm.v3i3.120.

X. Li, Y. Zhang, L. Wang, and Y. Liu, “Lightning Risk Warning Method Using Atmospheric Electric Field,” Atmosphere, vol. 14, no. 6, 2023, doi: 10.3390/atmos14061002.

A. Mostajabi, D. L. Finney, M. Rubinstein, and F. Rachidi, “Nowcasting Lightning Occurrence from Commonly Available Meteorological Parameters Using Machine Learning Techniques,” npj Climate and Atmospheric Science, vol. 2, no. 41, 2019, doi: 10.1038/s41612-019-0098-0.

J. Leinonen, U. Hamann, D. Nerini, U. Germann, and G. Franch, “Seamless Lightning Nowcasting with Recurrent-Convolutional Deep Learning,” Artificial Intelligence for the Earth Systems, vol. 1, no. 4, 2022, doi: 10.1175/AIES-D-22-0043.1.

G. Ehrensperger, T. Simon, G. J. Mayr, and T. Hell, “Identifying Lightning Processes in ERA5 Soundings with Deep Learning,” 2022.

T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794, doi: 10.1145/2939672.2939785.

R. Mitchell and E. Frank, “Accelerating the XGBoost Algorithm Using GPU Computing,” PeerJ Computer Science, vol. 3, 2017, doi: 10.7717/peerj-cs.127.

XGBoost Developers, “XGBoost Documentation,” 2026.

A. Sutaryani, S. Sunarno, and D. Djuniadi, “Perbandingan Performa Model Machine Learning dalam Prediksi Suhu di Semarang,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 3, 2024, doi: 10.23960/jitet.v12i3.4884.

F. H. Syahadah, R. T. Subagio, and P. Rizqiyah, “Penerapan XGBoost dalam Prediksi Pendaftaran Siswa Baru Bimbingan Belajar QSC di Kota Cirebon,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, no. 3S1, 2025, doi: 10.23960/jitet.v13i3S1.7998.

R. van de Schoot et al., “Bayesian Statistics and Modelling,” Nature Reviews Methods Primers, vol. 1, no. 1, 2021, doi: 10.1038/s43586-020-00001-2.

A. Gelman, J. B. Carlin, H. S. Stern, D. B. Dunson, A. Vehtari, and D. B. Rubin, Bayesian Data Analysis, 3rd ed. Boca Raton, FL, USA: CRC Press, 2013.

F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.